• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.

• Journal of Oriental Neuropsychiatry
• /
• v.34 no.3
• /
• pp.259-274
• /
• 2023

Objectives: The purpose of this study was to provide clinical evidence to support the use of auricular blood-letting therapy (ABT) for headaches. Methods: Studies were identified by a comprehensive search of five databases. Randomized controlled trials (RCTs) that investigated the effects of the ABT for headaches were included. Two authors independently extracted the data and assessed the methodological quality of the included studies using Cochrane's risk-of-bias tool. If two or more studies reported the same outcome, a meta-analysis was performed. Meta-analysis results for dichotomous variables are expressed as risk ratios (RRs) and 95% confidence intervals (CIs). Results: A total of eight RCTs were included in this review. The total effective rate (TER) was the most commonly used outcome measurement. Among the eight RCTs, five were included in the metaanalysis. The TER was not statistically significantly different in the ABT group compared to the medication group (two studies, n=55, RR=1.24, 95% CI: 0.78 to 1.96, p=0.36, I² =86%). However, the TER of the combined ABT and medication group was significantly different compared to the medication alone group (four studies, n=159, RR=1.23, 95% CI: 1.12 to 1.35, p<0.0001, I² = 0%). Pain and mental health-related outcomes in the combined ABT and medication group were significantly different from the control groups. The methodological quality of the included RCTs was generally low. Conclusions: ABT combined with medication may be effective for treating headaches. However, the number of studies included was small, so the results were insufficient, and statistically significant effects were not confirmed for a single implementation of ABT. Thus, well-designed further studies based on the findings of this study are recommended.

• Korean Journal of Radiology
• /
• v.23 no.10
• /
• pp.959-975
• /
• 2022

Objective: To investigate the agreement and reliability of estimating the volumes and normative percentiles (N%) of segmented brain regions among NeuroQuant (NQ), DeepBrain (DB), and FreeSurfer (FS) software programs, focusing on the comparison between NQ and DB. Materials and Methods: Three-dimensional T1-weighted images of 145 participants (48 healthy participants, 50 patients with mild cognitive impairment, and 47 patients with Alzheimer's disease) from a single medical center (SMC) dataset and 130 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset were included in this retrospective study. All images were analyzed with DB, NQ, and FS software to obtain volume estimates and N% of various segmented brain regions. We used Bland-Altman analysis, repeated measures ANOVA, reproducibility coefficient, effect size, and intraclass correlation coefficient (ICC) to evaluate inter-method agreement and reliability. Results: Among the three software programs, the Bland-Altman plot showed a substantial bias, the ICC showed a broad range of reliability (0.004-0.97), and repeated-measures ANOVA revealed significant mean volume differences in all brain regions. Similarly, the volume differences of the three software programs had large effect sizes in most regions (0.73-5.51). The effect size was largest in the pallidum in both datasets and smallest in the thalamus and cerebral white matter in the SMC and ADNI datasets, respectively. N% of NQ and DB showed an unacceptably broad Bland-Altman limit of agreement in all brain regions and a very wide range of ICC values (-0.142-0.844) in most brain regions. Conclusion: NQ and DB showed significant differences in the measured volume and N%, with limited agreement and reliability for most brain regions. Therefore, users should be aware of the lack of interchangeability between these software programs when they are applied in clinical practice.

• Journal of fish pathology
• /
• v.6 no.2
• /
• pp.111-122
• /
• 1993

The mechanism by which $V_H$ region gene segments is selected in B lymphocyte is not known. Moreover, evidence for both random and nonrandom expression of $V_H$ genes in matured B cells has been presented previously. In this report, the technique of in situ hybridization allowed us to analyze expressed $V_H$ gene families in normal B lymphocyte at the single cell level. The analysis of normal B cells in this study eliminated any posssible bias resulting from transformation protocols used previously and minimized limitation associated with sampling size. Therefore, an accurate measure of the functional and expressed $V_H$ gene repertoire in B lymphocyte could be made. One of the most important controls for the optimization of in situ hybridization is to establish probe concentration and washing stringency due to the degree of nucleotide sequence similarlity between different families which in some cases can be as high as 70%. When the radioactive $C{\mu}$ and $V_{H}J558$ RNA probes are tested on LPS-stimulated adult spleen cells, $2{\sim}4{\times}106cpm$/slide shows low background and reasonable frequency of specific positive cells. For the washing condition. 40~50% formamide at $54^{\circ}C$ is found to be optimum for the $C{\mu}$. $V_{H}S107$ and $V_{H}J558$ probes. The analyzed results clearly demonstrate that the level of each different $V_H$ gene family expression is dependent upon the complexity or size of that family. These findings are also extended to the level of $V_H$ gene family expression in separated bone marrow B cells depend upon the various stage of differentiation and conclude no preferential utilization of specific $V_H$ gene family. Thus, the utilization of VH gene segments in B lymphocyte of adult BALB/c mice is random and is not regulated or changed during the differentiation of B cells.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1996.05a
• /
• pp.1-3
• /
• 1996

시뮬레이션 기법을 이용한 시스템의 분석에 있어서 실험의 자동화는 현재 많은 연구와 개발이 진행 중인 분야이다. 컴퓨터와 정보통신 시스템에 대한 시뮬레이션의 예를 들어 보면, 수많은 모델을 대한 시뮬레이션을 수행할 경우 자동화된 실험의 제어가 요구되고 있다. 시뮬레이션 수행회수, 수행길이, 데이터 수집방법 등과 관련하여 시뮬레이션 실험방법이 자동화가 되지 않으면, 시뮬레이션 실험에 필요한 시간과 인적 자원이 상당히 커지게 되며 출력데이터에 대한 분석에 있어서도 어려움이 따르게 된다. 시뮬레이션 실험방법을 자동화하면서 효율적인 시뮬레이션 출력분석을 위해서는 시뮬레이션을 수행하는 경우에 항상 발생하는 초기편의 (initial bias)를 제거하는 문제가 선결되어야 한다. 시뮬레이션 출력분석에 사용되는 데이터들이 초기편의를 반영하지 않는 안정상태에서 수집된 것이어야만 실제 시스템에 대한 올바른 해석이 가능하다. 실제로 시뮬레이션 출력분석과 관련하여 가장 중요하면서도 어려운 문제는 시뮬레이션의 출력데이터가 이루는 추계적 과정 (stochastic process)의 안정상태 평균과 이 평균에 대한 신뢰구간(confidence interval: c. i.)을 구하는 것이다. 한 신뢰구간에 포함되어 있는 정보는 의사결정자에게 얼마나 정확하게 평균을 추정할 구 있는지 알려 준다. 그러나, 신뢰구간을 구성하는 일은 하나의 시뮬레이션으로부터 얻어진 출력데이터가 일반적으로 비정체상태(nonstationary)이고 자동상관(autocorrelated)되어 있기 때문에, 전통적인 통계적인 기법을 직접적으로 이용할 수 없다. 이러한 문제를 해결하기 위해 시뮬레이션 출력데이터 분석기법이 사용된다.본 논문에서는 초기편의를 제거하기 위해서 필요한 출력데이터의 제거시점을 찾는 새로운 기법으로, 유클리드 거리(Euclidean distance: ED)를 이용한 방법과 현재 패턴 분류(pattern classification) 문제에 널리 사용 중인 역전파 신경망(backpropagation neural networks: BNN) 알고리듬을 이용하는 방법을 제시한다. 이 기법들은 대다수의 기존의 기법과는 달리 시험수행(pilot run)이 필요 없으며, 시뮬레이션의 단일수행(single run) 중에 제거시점을 결정할 수 있다. 제거시점과 관련된 기존 연구는 다음과 같다. 콘웨이방법은 현재의 데이터가 이후 데이터의 최대값이나 최소값이 아니면 이 데이터를 제거시점으로 결정하는데, 알고기듬 구조상 온라인으로 제거시점 결정이 불가능하다. 콘웨이방법이 알고리듬의 성격상 온라인이 불가능한 반면, 수정콘웨이방법 (Modified Conway Rule: MCR)은 현재의 데이터가 이전 데이터와 비교했을 때 최대값이나 최소값이 아닌 경우 현재의 데이터를 제거시점으로 결정하기 때문에 온라인이 가능하다. 평균교차방법(Crossings-of-the-Mean Rule: CMR)은 누적평균을 이용하면서 이 평균을 중심으로 관측치가 위에서 아래로, 또는 아래서 위로 교차하는 회수로 결정한다. 이 기법을 사용하려면 교차회수를 결정해야 하는데, 일반적으로 결정된 교차회수가 시스템에 상관없이 일반적으로 적용가능하지 않다는 문제점이 있다. 누적평균방법(Cumulative-Mean Rule: CMR2)은 여러 번의 시험수행을 통해서 얻어진 출력데이터에 대한 총누적평균(grand cumulative mean)을 그래프로 그린 다음, 안정상태인 점을 육안으로 결정한다. 이 방법은 여러 번의 시뮬레이션을 수행에서 얻어진 데이터들의 평균들에 대한 누적평균을 사용하기 매문에 온라인 제거시점 결정이 불가능하며, 작업자가 그래프를 보고 임의로 결정해야 하는 단점이 있다. Welch방법(Welch's Method: WM)은 브라운 브리지(Brownian bridge) 통계량()을 사용하는데, n이 무한에 가까워질 때, 이 브라운 브리지 분포(Brownian bridge distribution)에 수렴하는 성질을 이용한다. 시뮬레이션 출력데이터를 가지고 배치를 구성한 후 하나의 배치를 표본으로 사용한다. 이 기법은 알고리듬이 복잡하고, 값을 추정해야 하는 단점이 있다. Law-Kelton방법(Law-Kelton's Method: LKM)은 회귀 (regression)이론에 기초하는데, 시뮬레이션이 종료된 후 누적평균데이터에 대해서 회귀직선을 적합(fitting)시킨다. 회귀직선의 기울기가 0이라는 귀무가설이 채택되면 그 시점을 제거시점으로 결정한다. 일단 시뮬레이션이 종료된 다음, 데이터가 모아진 순서의 반대 순서로 데이터를 이용하기 때문에 온라인이 불가능하다. Welch절차(Welch's Procedure: WP)는 5회이상의 시뮬레이션수행을 통해 수집한 데이터의 이동평균을 이용해서 시각적으로 제거시점을 결정해야 하며, 반복제거방법을 사용해야 하기 때문에 온라인 제거시점의 결정이 불가능하다. 또한, 한번에 이동할 데이터의 크기(window size)를 결정해야 한다. 지금까지 알아 본 것처럼, 기존의 방법들은 시뮬레이션의 단일 수행 중의 온라인 제거시점 결정의 관점에서는 미약한 면이 있다. 또한, 현재의 시뮬레이션 상용소프트웨어는 작업자로 하여금 제거시점을 임의로 결정하도록 하기 때문에, 실험중인 시스템에 대해서 정확하고도 정량적으로 제거시점을 결정할 수 없게 되어 있다. 사용자가 임의로 제거시점을 결정하게 되면, 초기편의 문제를 효과적으로 해결하기 어려울 뿐만 아니라, 필요 이상으로 너무 많은 양을 제거하거나 초기편의를 해결하지 못할 만큼 너무 적은 양을 제거할 가능성이 커지게 된다. 또한, 기존의 방법들의 대부분은 제거시점을 찾기 위해서 시험수행이 필요하다. 즉, 안정상태 시점만을 찾기 위한 시뮬레이션 수행이 필요하며, 이렇게 사용된 시뮬레이션은 출력분석에 사용되지 않기 때문에 시간적인 손실이 크게 된다.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.53 no.3
• /
• pp.46-55
• /
• 2016

This work proposes a 13b 100MS/s 45nm CMOS ADC with a high dynamic performance for IF-domain high-speed signal processing systems based on a four-step pipeline architecture to optimize operating specifications. The SHA employs a wideband high-speed sampling network properly to process high-frequency input signals exceeding a sampling frequency. The SHA and MDACs adopt a two-stage amplifier with a gain-boosting technique to obtain the required high DC gain and the wide signal-swing range, while the amplifier and bias circuits use the same unit-size devices repeatedly to minimize device mismatch. Furthermore, a separate analog power supply voltage for on-chip current and voltage references minimizes performance degradation caused by the undesired noise and interference from adjacent functional blocks during high-speed operation. The proposed ADC occupies an active die area of $0.70mm^2$, based on various process-insensitive layout techniques to minimize the physical process imperfection effects. The prototype ADC in a 45nm CMOS demonstrates a measured DNL and INL within 0.77LSB and 1.57LSB, with a maximum SNDR and SFDR of 64.2dB and 78.4dB at 100MS/s, respectively. The ADC is implemented with long-channel devices rather than minimum channel-length devices available in this CMOS technology to process a wide input range of $2.0V_{PP}$ for the required system and to obtain a high dynamic performance at IF-domain input signal bands. The ADC consumes 425.0mW with a single analog voltage of 2.5V and two digital voltages of 2.5V and 1.1V.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.1-32
• /
• 2018

In addition to stakeholders including managers, employees, creditors, and investors of bankrupt companies, corporate defaults have a ripple effect on the local and national economy. Before the Asian financial crisis, the Korean government only analyzed SMEs and tried to improve the forecasting power of a default prediction model, rather than developing various corporate default models. As a result, even large corporations called 'chaebol enterprises' become bankrupt. Even after that, the analysis of past corporate defaults has been focused on specific variables, and when the government restructured immediately after the global financial crisis, they only focused on certain main variables such as 'debt ratio'. A multifaceted study of corporate default prediction models is essential to ensure diverse interests, to avoid situations like the 'Lehman Brothers Case' of the global financial crisis, to avoid total collapse in a single moment. The key variables used in corporate defaults vary over time. This is confirmed by Beaver (1967, 1968) and Altman's (1968) analysis that Deakins'(1972) study shows that the major factors affecting corporate failure have changed. In Grice's (2001) study, the importance of predictive variables was also found through Zmijewski's (1984) and Ohlson's (1980) models. However, the studies that have been carried out in the past use static models. Most of them do not consider the changes that occur in the course of time. Therefore, in order to construct consistent prediction models, it is necessary to compensate the time-dependent bias by means of a time series analysis algorithm reflecting dynamic change. Based on the global financial crisis, which has had a significant impact on Korea, this study is conducted using 10 years of annual corporate data from 2000 to 2009. Data are divided into training data, validation data, and test data respectively, and are divided into 7, 2, and 1 years respectively. In order to construct a consistent bankruptcy model in the flow of time change, we first train a time series deep learning algorithm model using the data before the financial crisis (2000~2006). The parameter tuning of the existing model and the deep learning time series algorithm is conducted with validation data including the financial crisis period (2007~2008). As a result, we construct a model that shows similar pattern to the results of the learning data and shows excellent prediction power. After that, each bankruptcy prediction model is restructured by integrating the learning data and validation data again (2000 ~ 2008), applying the optimal parameters as in the previous validation. Finally, each corporate default prediction model is evaluated and compared using test data (2009) based on the trained models over nine years. Then, the usefulness of the corporate default prediction model based on the deep learning time series algorithm is proved. In addition, by adding the Lasso regression analysis to the existing methods (multiple discriminant analysis, logit model) which select the variables, it is proved that the deep learning time series algorithm model based on the three bundles of variables is useful for robust corporate default prediction. The definition of bankruptcy used is the same as that of Lee (2015). Independent variables include financial information such as financial ratios used in previous studies. Multivariate discriminant analysis, logit model, and Lasso regression model are used to select the optimal variable group. The influence of the Multivariate discriminant analysis model proposed by Altman (1968), the Logit model proposed by Ohlson (1980), the non-time series machine learning algorithms, and the deep learning time series algorithms are compared. In the case of corporate data, there are limitations of 'nonlinear variables', 'multi-collinearity' of variables, and 'lack of data'. While the logit model is nonlinear, the Lasso regression model solves the multi-collinearity problem, and the deep learning time series algorithm using the variable data generation method complements the lack of data. Big Data Technology, a leading technology in the future, is moving from simple human analysis, to automated AI analysis, and finally towards future intertwined AI applications. Although the study of the corporate default prediction model using the time series algorithm is still in its early stages, deep learning algorithm is much faster than regression analysis at corporate default prediction modeling. Also, it is more effective on prediction power. Through the Fourth Industrial Revolution, the current government and other overseas governments are working hard to integrate the system in everyday life of their nation and society. Yet the field of deep learning time series research for the financial industry is still insufficient. This is an initial study on deep learning time series algorithm analysis of corporate defaults. Therefore it is hoped that it will be used as a comparative analysis data for non-specialists who start a study combining financial data and deep learning time series algorithm.

• Korean small business review
• /
• v.31 no.2
• /
• pp.19-37
• /
• 2009

The purpose of this research is to explore differences between small and medium-sized companies and large-sized companies in the impact of human resource innovativeness(HRI), learning orientation(LO), and HRI-LO interaction on innovation effect and business performance. Although learning orientation has long been considered as a key factor influencing good performance of a business, little research was devoted to exploring the effect of HRI-LO interaction on innovation effect and business performance. In this study, it is investigated whether there is a synergy effect between innovative human workforce and learning orientation corporate culture, in addition to each by itself, to generate good business performance as well as a success of new innovations in the market. Research hypotheses were as follows, including H1) human resource innovativeness(HRI), learning orientation(LO), and interactions of HRI and LO(HRI-LO interaction) positively affect innovation effect, H2) there is a difference of the effect of HRI, LO, and HRI-LO interaction on innovation effect between large-sized and small-sized companies, H3) HRI, LO, HRI-LO interaction, innovation effect positively affect business performance, and H4) there is a difference of the effect of HRI, LO, HRI-LO interaction, and innovation effect on business performance between large-sized and small-sized companies. Data were obtained from 479 practitioners through a web survey since the web survey is an efficient method to collect a national data at a variety of fields. A single respondent from a company was allowed to participate in the study after checking whether they have more than 5-year work experiences in the company. To check whether a common source bias is existed in the sample, additional data from a convenient sample of 97 companies were gathered through the traditional survey method, and were used to confirm correlations between research variables of the original sample and the additional sample. Data were divided into two groups according to company size, such as 352 small and medium-sized companies with less than 300 employees and 127 large-sized companies with 300 or more employees. Data were analyzed through t-test and regression analyses. HRI which is the innovativeness of human resources in the company was measured with 9 items assessing the innovativenss of practitioners in staff, manager, and executive-level positions. LO is the company's effort to encourage employees' development, sharing, and utilizing of knowledge through consistent learning. LO was measured by 18 items assessing commitment to learning, vision sharing, and open-mindedness. Innovation effect which assesses a success of new products/services in the market, was measured with 3 items. Business performance was measured by respondents' evaluations on profitability, sales increase, market share, and general business performance, compared to other companies in the same field. All items were measured by using 6-point Likert scales. Means of multiple items measuring a construct were used as variables based on acceptable reliability and validity. To reduce multi-collinearity problems generated on the regression analysis of interaction terms, centered data were used for HRI, LO, and Innovation effect on regression analyses. In group comparison, large-sized companies were superior on annual sales, annual net profit, the number of new products/services in the last 3 years, the number of new processes advanced in the last 3 years, and the number of R&D personnel, compared to small and medium-sized companies. Also, large-sized companies indicated a higher level of HRI, LO, HRI-LO interaction, innovation effect and business performance than did small and medium-sized companies. The results indicate that large-sized companies tend to have more innovative human resources and invest more on learning orientation than did small-sized companies, therefore, large-sized companies tend to have more success of a new product/service in the market, generating better business performance. In order to test research hypotheses, a series of multiple-regression analysis was conducted. In the regression analysis examining the impact on innovation effect, important results were generated as : 1) HRI, LO, and HRI-LO affected innovation effect, and 2) company size indicated a moderating effect. Based on the result, the impact of HRI on innovation effect would be greater in small and medium-sized companies than in large-sized companies whereas the impact of LO on innovation effect would be greater in large-sized companies than in small and medium-sized companies. In other words, innovative workforce would be more important in making new products/services that would be successful in the market for small and medium-sized companies than for large-sized companies. Otherwise, learning orientation culture would be more effective in making successful products/services for large-sized companies than for small and medium-sized companies. Based on these results, research hypotheses 1 and 2 were supported. In the analysis of a regression examining the impact on business performance, important results were generated as : 1) innovation effect, LO, and HRI-LO affected business performance, 2) HRI by itself did not have a direct effect on business performance regardless of company size, and 3) company size indicated a moderating effect. Specifically, an effect of the HRI-LO interaction on business performance was stronger in large-sized companies than in small and medium-sized companies. It means that the synergy effect of innovative human resources and learning orientation culture tends to be stronger as company is larger. Referring to these result, research hypothesis 3 was partially supported whereas hypothesis 4 was supported. Based on research results, implications for companies were generated. Regardless of company size, companies need to develop the learning orientation corporate culture as well as human resources' innovativeness together in order to achieve successful development of innovative products and services as well as to improve sales and profits. However, the effectiveness of the HRI-LO interaction would be varied by company size. Specifically, the synergy effect of HRI-LO was stronger to make a success of new products/services in small and medium-sized companies than in large-sized companies. However, the synergy effect of HRI-LO was more effective to increase business performance of large-sized companies than that of small and medium-sized companies. In the case of small and medium-sized companies, business performance was achieved more through the success of new products/services than much directly affected by HRI-LO. The most meaningful result of this study is that the effect of HRI-LO interaction on innovation effect and business performance was confirmed. It was often ignored in the previous research. Also, it was found that the innovativeness of human workforce would not directly influence in generating good business performance, however, innovative human resources would indirectly affect making good business performance by contributing to achieving the development of new products/services that would be successful in the market. These findings would provide valuable managerial implications specifically in regard to the development of corporate culture and education program of small and medium-sized as well as large-sized companies in a variety of fields.

• Journal of the Korean Society of Costume
• /
• v.4
• /
• pp.87-114
• /
• 1981

A costume reveals the social characteristics of the era in which it is worn, thus we can say that the history of change of the costume is the history of change of the living culture of the era. Since the Three States era, the costume structure of this country had been affected by the costume system of the China's historical dynasties in the form of the grant therefrom because of geographical conditions, which affection was conspicuous for the bureaucrat class, particularly including but not limited to the Kings' familities. Such a grant of the costume for the bureaucrat class (i.e., official uniform) was first given by the Dang-dynasty at the age of Queen Jinduck, the 28th of the Shilla-dynasty. Since then, the costume for the bureaucrats had consecutively been affected as the ages had gone from the unified Shilla, to the Koryo and to the Yi-dynasty. As the full costumes officially used by government officials (generally called "Baek Gwan") in the Yidynasty, there existed Jo-bok, Gong-bok and Sang-bok. Of such official costumes, Gong-bok was worn at the time of conducting official affairs of the dynasty, making a respectful visit for the expression of thanks or meeting diplomatic missions of foreign countries. It appears no study was made yet with regard to the Gong-bok while the studies on the Jo-bok and the Sangbok were made. Therefore, this article is, by rendering a study and research on the styles of costumes of civil servants' stone images erected at the Kings' tombs of the Yi-dynasty, to help the persons concerned understand the Gong-bok, one of the official costume for Baek Kwan of that age and further purports to specifically identify the styles and changes of the Gong-bok, worn by Baek Gwan during the Yi-dynasty, consisting of the Bok-doo (a hat, four angled and two storied with flat top), Po (gown), Dae (belt), and Hol (small and thin plate which was officially held by the government officials in hand, showing the courtesy to and writing brief memorandums before the King) and Hwa (shoes). For that purpose, I investigated by actually visiting the tombs of the Kings of the Yi-dynasty including the Geonwon-neung, the tomb of the first King Tae-jo and the You-neung, the tomb of the 27th King Soon-jong as well as the tombs of the lawful wives and concubines of various Kings, totalling 29 tombs and made reference to relevant books and records. Pursuant. to this study, of the 29 Kings' tombs the costume styles of civil servants' stone images erected at the 26 Kings' tombs are those of Gong-bok for Baek-gwan of the Yi-dynasty wearing Bok-doo as a hat and Ban-ryeong or Dan-ryenog Po as a gown with Dae, holding Hol in hand and wearing shoes. Other than those of the 26 tombs, the costume styles of the Ryu-neung, the tomb of the Moon-jo who was the first son of 23rd King Soon-jo and given the King's title after he died and of the You-neung, the tomb of the 27th King Soon-jong are those of Jobok with Yang-gwan (a sort of hat having stripes erected, which is different from the Bok-doo), and that of the Hong-neung, the tomb of the 26th King Go-jong shows an exceptional one wearing Yang-gwan and Ban-ryeong Po ; these costume styles other than Gongbok remain as the subject for further study. Gong-bok which is the costume style of civil servants' stone images of most of the Kings' tombs had not been changed in its basic structure for about 500 years of the Yi-dynasty and Koryo categorized by the class of officials pursuant to the color of Po and materials of Dae and Hol. Summary of this costume style follows: (1) Gwan-mo (hat). The Gwan-mo style of civil servants' stone images of the 26 Kings' tombs, other than Ryu-neung, Hong-neung and You-neung which have Yang-gwan, out of the 29 Kings' tombs of the Yi-dynasty reveals the Bok-doo with four angled top, having fore-part and back-part divided. Back part of the Bok-doo is double the fore-part in height. The expression of the Gak (wings of the Bokdoo) varies: the Gyo-gak Bok-doo in that the Gaks, roundly arisen to the direction of the top, are clossed each other (tombs of the Kings Tae-jong), the downward style Jeon-gak Bok-doo in that soft Gaks are hanged on the shoulders (tombs of the Kings Joong-jong and Seong-jong) and another types of Jeon-gak Bok-doo having Gaks which arearisen steeply or roundly to the direction of top and the end of which are treated in a rounded or straight line form. At the lower edge one protrusive line distinctly reveals. Exceptionally, there reveals 11 Yang-gwan (gwan having 11 stripes erected) at the Ryu-neung of the King Moon-jo, 9 Yang-gwan at the Hong-neung of the King Go-jong and 11 Yang-gwan at the You-neung of the King Soon-jong; noting that the Yang-gwan of Baek Kwan, granted by the Myeong-dynasty of the China during the Yi-dynasty, was in the shape of 5 Yang-gwan for the first Poom (class) based on the principle of "Yideung Chaegang" (gradual degrading for secondary level), the above-mentioned Yang-gwans are very contrary to the principle and I do not touch such issue in this study, leaving for further study. (2) Po (gown). (a) Git (collar). Collar style of Po was the Ban-ryeong (round collar) having small neck-line in the early stage and was changed to the Dan-ryeong (round collar having deep neck-line) in the middle of the: dynasty. In the Dan-ryeong style of the middle era (shown at the tomb of the King Young-jo); a, thin line such as bias is shown around the internal side edge and the width of collar became wide a little. It is particularly noted that the Ryu-neung established in the middle stage and the You-neung in the later stage show civil servants in Jo-bok with the the Jikryeong (straight collar) Po and in case of the Hong-neung, the Hong-neung, the tomb of the King Go-jong, civil servants, although they wear Yang-gwan, are in the Ban-ryeong Po with Hoo-soo (back embroidery) and Dae and wear shoes as used in the Jo-bok style. As I could not make clear the theoretical basis of why the civil servants' costume styles revealed, at these tombs of the Kings are different from those of other tombs, I left this issue for further study. It is also noted that all the civil servants' stone images show the shape of triangled collar which is revealed over the Godae-git of Po. This triangled collar, I believe, would be the collar of the Cheomri which was worn in the middle of the Po and the underwear, (b) Sleeve. The sleeve was in the Gwan-soo (wide sleeve) style. having the width of over 100 centimeter from the early stage to the later stage arid in the Doo-ri sleeve style having the edge slightly rounded and we can recognize that it was the long sleeve in view of block fold shaped protrusive line, expressed on the arms. At the age of the King Young-jo, the sleeve-end became slightly narrow and as a result, the lower line of the sleeve were shaped curved. We can see another shape of narrow sleeve inside the wide sleeve-end, which should be the sleeve of the Cheom-ri worn under the Gong-bok. (c) Moo. The Moo revealed on the Po of civil servants' stone images at the age of the King Sook-jong' coming to the middle era. Initially the top of the Moo was expressed flat but the Moo was gradually changed to the triangled shape with the acute top. In certain cases, top or lower part of the Moo are not reveald because of wear and tear. (d) Yeomim. Yeomim (folding) of the Po was first expressed on civil servants' stone images of the Won-neung, the tomb of the King Young-jo and we can seemore delicate expression of the Yeomim and Goreum (stripe folding and fixing the lapel of the Po) at the tomb of the Jeongseong-wanghoo, the wife of the King Young-jo, At the age of the King Soon-jo, we can see the shape of Goreum similar to a string rather than the Goreum and the upper part of the Goreum which fixes Yeomim was expressed on the right sleeve. (3) Dae. Dae fixed on the Po was placed half of the length of Po from the shoulders in the early stage. Thereafter, at the age of the King Hyeon-jong it was shown on the slightly upper part. placed around one third of the length of Po. With regard to the design of Dae, all the civil servants' stone images of the Kings' tombs other than those of the Geonwon-neung of the King Tae-jo show single or double protrusive line expressed at the edge of Dae and in the middle of such lines, cloud pattern, dangcho (a grass) pattern, chrysanthemum pattern or other various types of flowery patterns were designed. Remaining portion of the waist Dae was hanged up on the back, which was initially expressed as directed from the left to the right but thereafter expressed. without orderly fashion,. to the direction of the left from the right and vice versa, Dae was in the shape of Yaja Dae. In this regard, an issue of when or where such a disorderly fashion of the direction of the remaining portion of waist Dae was originated is also presented to be clarified. In case of the Ryuneung, Hong-neung and You-neung which have civil servants' stone images wearing exceptional costume (Jo-bok), waist Dae of the Ryu-neung and Hong-neung are designed in the mixture of dual cranes pattern, cosecutive beaded pattern and chrvsenthemum pattern and that of You-neung is designed in cloud pattern. (4) Hol. Although materials of the Hol held in hand of civil servants' stone images are not identifiable, those should be the ivory Hol as all the Baek Gwan's erected as stone images should be high class officials. In the styles, no significant changes were found, however the Hol's expressed on civil servants' stone images of the Yi-dynasty were shaped in round top and angled bottom or round top and bottom. Parcicularly, at the age of the King Young-jo the Hol was expressed in the peculiar type with four angles all cut off. (5) Hwa (shoes). As the shoes expressed on civil servants' stone images are covered with the lower edges of the Po, the styles thereof are not exactly identifiable. However, reading the statement "black leather shoes for the first class (1 Poom) to ninth class (9 Poom)," recorded in the Gyeongkook Daejon, we can believe that the shoes were worn. As the age went on, the front tips of the shoes were soared and particularly, at the Hong-neung of the King Go-jong the shoes were obviously expressed with modern sense as the country were civilized.